submission_id: trace2333-mistral-align-_8132_v1
developer_uid: Trace2333
alignment_samples: 9428
alignment_score: -0.28239305774619805
best_of: 8
celo_rating: 1252.44
display_name: trace2333-mistral-align-_8132_v1
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.06, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Trace2333/mistral_align_namo_1448
latencies: [{'batch_size': 1, 'throughput': 0.7024851928772059, 'latency_mean': 1.423459416627884, 'latency_p50': 1.422094464302063, 'latency_p90': 1.5869778394699097}, {'batch_size': 3, 'throughput': 1.334092890538201, 'latency_mean': 2.2467334151268004, 'latency_p50': 2.2446675300598145, 'latency_p90': 2.492887449264526}, {'batch_size': 5, 'throughput': 1.5866624396563926, 'latency_mean': 3.1304232692718506, 'latency_p50': 3.1094034910202026, 'latency_p90': 3.5016963481903076}, {'batch_size': 6, 'throughput': 1.603655847035458, 'latency_mean': 3.7288178753852845, 'latency_p50': 3.7559107542037964, 'latency_p90': 4.162970113754272}, {'batch_size': 8, 'throughput': 1.574886432737673, 'latency_mean': 5.03738531589508, 'latency_p50': 5.045974850654602, 'latency_p90': 5.7134216070175174}, {'batch_size': 10, 'throughput': 1.579658977136668, 'latency_mean': 6.291908217668533, 'latency_p50': 6.324097394943237, 'latency_p90': 7.196389675140381}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: Trace2333/mistral_align_
model_name: trace2333-mistral-align-_8132_v1
model_num_parameters: 12772070400.0
model_repo: Trace2333/mistral_align_namo_1448
model_size: 13B
num_battles: 9428
num_wins: 5053
propriety_score: 0.7477110885045778
propriety_total_count: 983.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.61
timestamp: 2024-09-06T12:02:33+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5359567246499788
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name trace2333-mistral-align-8132-v1-mkmlizer
Waiting for job on trace2333-mistral-align-8132-v1-mkmlizer to finish
trace2333-mistral-align-8132-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-mistral-align-8132-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-mistral-align-8132-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-mistral-align-8132-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-mistral-align-8132-v1-mkmlizer: ║       /___/                                                         ║
trace2333-mistral-align-8132-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-mistral-align-8132-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-mistral-align-8132-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-mistral-align-8132-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-mistral-align-8132-v1-mkmlizer: ║                                                                     ║
trace2333-mistral-align-8132-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-mistral-align-8132-v1-mkmlizer: Downloaded to shared memory in 49.009s
trace2333-mistral-align-8132-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjdlbkha6, device:0
trace2333-mistral-align-8132-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-mistral-align-8132-v1-mkmlizer: quantized model in 36.269s
trace2333-mistral-align-8132-v1-mkmlizer: Processed model Trace2333/mistral_align_namo_1448 in 85.279s
trace2333-mistral-align-8132-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-mistral-align-8132-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-mistral-align-8132-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1
trace2333-mistral-align-8132-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1/config.json
trace2333-mistral-align-8132-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1/special_tokens_map.json
trace2333-mistral-align-8132-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1/tokenizer_config.json
trace2333-mistral-align-8132-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1/tokenizer.json
trace2333-mistral-align-8132-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-mistral-align-8132-v1/flywheel_model.0.safetensors
trace2333-mistral-align-8132-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:07, 50.82it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:04, 83.40it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:03, 93.35it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:03, 80.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 83.41it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:14, 20.33it/s]
Loading 0:  19%|█▉        | 70/363 [00:01<00:11, 26.17it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 32.18it/s]
Loading 0:  24%|██▍       | 88/363 [00:02<00:07, 37.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 43.53it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 51.06it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:04, 58.06it/s]
Loading 0:  34%|███▍      | 124/363 [00:02<00:03, 63.08it/s]
Loading 0:  37%|███▋      | 133/363 [00:02<00:03, 62.36it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:10, 20.10it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:08, 25.92it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 36.73it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:04, 41.47it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:03, 47.72it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 53.33it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 60.37it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 66.44it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:06, 20.97it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 31.35it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 37.06it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 42.38it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:01, 49.53it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:01, 60.38it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 64.46it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 63.52it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:00, 62.67it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 20.18it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 25.52it/s]
Loading 0:  90%|█████████ | 328/363 [00:08<00:01, 32.60it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 39.51it/s]
Loading 0:  95%|█████████▌| 346/363 [00:08<00:00, 44.92it/s]
Loading 0:  98%|█████████▊| 355/363 [00:08<00:00, 52.02it/s]
Loading 0: 100%|██████████| 363/363 [00:15<00:00,  4.24it/s]
                                                            

Job trace2333-mistral-align-8132-v1-mkmlizer completed after 115.19s with status: succeeded
Stopping job with name trace2333-mistral-align-8132-v1-mkmlizer
Pipeline stage MKMLizer completed in 116.28s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service trace2333-mistral-align-8132-v1
Waiting for inference service trace2333-mistral-align-8132-v1 to be ready
Inference service trace2333-mistral-align-8132-v1 ready after 150.39921855926514s
Pipeline stage MKMLDeployer completed in 150.84s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission zonemercy-lexical-nemo-_1518_v23: ('http://zonemercy-lexical-nemo-1518-v23-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Received healthy response to inference request in 2.773545026779175s
Failed to get response for submission neversleep-noromaid-v0_8068_v150: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Received healthy response to inference request in 2.029822587966919s
Received healthy response to inference request in 1.6436614990234375s
Received healthy response to inference request in 2.3568294048309326s
Received healthy response to inference request in 2.229405641555786s
5 requests
0 failed requests
5th percentile: 1.7208937168121339
10th percentile: 1.79812593460083
20th percentile: 1.9525903701782226
30th percentile: 2.0697391986846925
40th percentile: 2.149572420120239
50th percentile: 2.229405641555786
60th percentile: 2.2803751468658446
70th percentile: 2.331344652175903
80th percentile: 2.440172529220581
90th percentile: 2.6068587779998778
95th percentile: 2.6902019023895263
99th percentile: 2.7568764019012453
mean time: 2.20665283203125
Pipeline stage StressChecker completed in 12.37s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.77s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-mistral-align-8132-v1-profiler
Waiting for inference service trace2333-mistral-align-8132-v1-profiler to be ready
Inference service trace2333-mistral-align-8132-v1-profiler ready after 150.36049723625183s
Pipeline stage MKMLProfilerDeployer completed in 150.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-mistral-ald36518ed2cd2ac1bf9929424448a3714-deplot9pzj:/code/chaiverse_profiler_1725624624 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-mistral-ald36518ed2cd2ac1bf9929424448a3714-deplot9pzj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725624624 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725624624/summary.json'
kubectl exec -it trace2333-mistral-ald36518ed2cd2ac1bf9929424448a3714-deplot9pzj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725624624/summary.json'
Pipeline stage MKMLProfilerRunner completed in 946.35s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-mistral-align-8132-v1-profiler is running
Tearing down inference service trace2333-mistral-align-8132-v1-profiler
Service trace2333-mistral-align-8132-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.11s
Shutdown handler de-registered
trace2333-mistral-align-_8132_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics